Asymmetries in Volatility: An Empirical Study for the Peruvian Stock and Forex Market
Symmetric and asymmetric autoregressive conditional heteroskedasticity models and stochastic volatility models are applied to daily data of Peruvian stock and Forex markets returns for the period January 5, 1998 until December 30, 2011. Following the approach developed by Omori et al. (2007), Bayesian estimation methodology is used with different structures in the behavior of the disturbance terms. The results suggest the presence of asymmetric effects in both markets. In the stock market, we find that negative shocks generate higher volatility than positive shocks. In the Forex market, shocks related to episodes of depreciation create higher uncertainty in comparison with episodes of appreciation. Thus, the Central Reserve Bank faces relatively major difficulties in its intention of smoothing Forex volatility. The model with the best fit in both returns is the Asymmetric Stochastic Volatility with Normal errors. The stock market returns have greater periods of volatility; however, both markets react to shocks in the economy, as they display similar patterns and have a significant correlation for the sample period studied.
Asymmetries, Bayesian Estimation, EGARCH, Forex Re- turns, GARCH, Stochastic Volatility, Stock Returns
C11, C12, C53, G12